Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1076 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6160. Min Range: -1.6160

Max Act: 1.6160. Min Act: -0.0000

Data Index: 63394 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 1.6160. Min Range: -1.6160

Max Act: 1.4452. Min Act: -0.0000

Data Index: 63335 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 1.6160. Min Range: -1.6160

Max Act: 1.1043. Min Act: -0.0000

Data Index: 977869 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.6160. Min Range: -1.6160

Max Act: 1.1306. Min Act: -0.0000

Data Index: 1143641 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.6160. Min Range: -1.6160

Max Act: 1.0824. Min Act: -0.0000

Data Index: 849271 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8959. Min Act: -0.0000

Data Index: 969496 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.9778. Min Act: -0.0000

Data Index: 369621 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1250513 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1213130 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1354381 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.9080. Min Act: -0.0000

Data Index: 709894 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1237269 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1256837 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8708. Min Act: -0.0000

Data Index: 795114 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1352946 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8303. Min Act: -0.0000

Data Index: 608617 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8138. Min Act: -0.0000

Data Index: 167202 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1614364 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.7762. Min Act: -0.0000

Data Index: 280593 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 1.6160. Min Range: -1.6160

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1530787 (Python Code)

Max Activating Token Index: 143